Real-time crash prediction research attempted the use of data from inductive loop detectors; however, no safety analysis has been carried out using traffic data from one of the most growing nonintrusive surveillance systems, i.e., the tag readers on toll roads known as automatic vehicle identification (AVI) systems. In this paper, for the first time, the identification of freeway locations with high crash potential has been examined using real-time speed data collected from AVI. Travel time and space mean speed data collected by AVI systems and crash data of a total of 78 mi on the expressway network in Orlando in 2008 were collected. Utilizing a random forest technique for significant variable selection and stratified matched case-control to account for the confounding effects of location, time, and season, the log odds of crash occurrence were calculated. The length of the AVI segment was found to be a crucial factor that affects the usefulness of the AVI traffic data. While the results showed that the likelihood of a crash is statistically related to speed data obtained from AVI segments within an average length of 1.5 mi and crashes can be classified with about 70% accuracy, all speed parameters obtained from AVI systems spaced at 3 mi or more apart were found to be statistically insignificant to identify crash-prone conditions. The findings of this study illustrate a promising real-time safety application for one of the most widely used and already present intelligent transportation systems, with many possible advances in the context of advanced traffic management.

This study investigated the effect of the interaction between roadway geometric features and real-time weather and traffic data on the occurrence of crashes on a mountainous freeway. The Bayesian logistic regression technique was used to link a total of 301 crash occurrences on I-70 in Colorado with the space mean speed collected in real time from an automatic vehicle identification (AVI) system and real-time weather and roadway geometry data. The results suggested that the inclusion of roadway geometrics and real-time weather with data from an AV I system in the context of active traffic management systems was essential, in particular with roadway sections characterized by mountainous terrain and adverse weather. The modeling results showed that the geometric factors were significant in the dry and the snowy seasons and that the likelihood of a crash could double during the snowy season because of the interaction between the pavement condition and steep grades. The 6-min average speed at the crash segment during the 6 to 12 min before the crash and the visibility 1 h before the crash were found to be significant during the dry season, whereas the logarithms of the coefficient of variation in speed at the crash segment during the 6 to 12 min before the crash, the visibility 1 h before the crash, as well as the precipitation 10 min before the crash were found to be significant during the snowy season. The results from the two models suggest that different active traffic management strategies should be in place during these two distinct seasons.